AI Risk Wire

Cases · Who discovered it: an independent researcher or journalist · Severity: moderate · What set it off: hidden instructions in its input

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Prompt-injected email assistant summary pushes employee toward fraudulent vendor paymentmoderate · earliest source 2026-10-07security breachmoderate2026-10-07
Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document
Anthropicmoderate · earliest source 2026-08-27
security breachmoderate2026-08-27

Showing 1–2 of 2. Or take the JSON.